paper-with-me

Papers

Securing Biomedical Images from Unauthorized Training with Anti-Learning Perturbation

2023-03-05 · Yixin Liu, Haohui Ye, Kai Zhang, Lichao Sun

The volume of open-source biomedical data has been essential to the development of various spheres of the healthcare community since more free' data can provide individual researchers more chances to contribute. However, institutions often hesitate to share their data with the public due to the risk of data exploitation by unauthorized third parties for another commercial usage (e.g., training AI models). This phenomenon might hinder the development of the whole healthcare research community. To address this concern, we propose a novel approach termed unlearnable biomedical image' for protecting biomedical data by injecting imperceptible but delusive noises into the data, making them unexploitable for AI models. We formulate the problem as a bi-level optimization and propose three kinds of anti-learning perturbation generation approaches to solve the problem. Our method is an important step toward encouraging more institutions to contribute their data for the long-term development of the research community.

📄 PDF Abstract BibTeX arXiv:2303.02559

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Medical Unlearnable Examples: Securing Medical Data from Unauthorized Training via Sparsity-Aware Local Masking

2024-03-15 · Weixiang Sun, Yixin Liu, Zhiling Yan, Kaidi Xu 외

The rapid expansion of AI in healthcare has led to a surge in medical data generation and storage, boosting medical AI development. However, fears of unauthorized use, like training commercial AI models, hinder researche…

Securing Fixed Neural Network Steganography

2023-09-18 · Zicong Luo, Sheng Li, Guobiao Li, Zhenxing Qian 외

Image steganography is the art of concealing secret information in images in a way that is imperceptible to unauthorized parties. Recent advances show that is possible to use a fixed neural network (FNN) for secret embed…

Image Steganography

Encrypted Prompt: Securing LLM Applications Against Unauthorized Actions

2025-03-29 · Shih-Han Chan

Security threats like prompt injection attacks pose significant risks to applications that integrate Large Language Models (LLMs), potentially leading to unauthorized actions such as API misuse. Unlike previous approache…

DIAGNOSIS: Detecting Unauthorized Data Usages in Text-to-image Diffusion Models

2023-07-06 · Zhenting Wang, Chen Chen, Lingjuan Lyu, Dimitris N. Metaxas 외

Recent text-to-image diffusion models have shown surprising performance in generating high-quality images. However, concerns have arisen regarding the unauthorized data usage during the training or fine-tuning process. O…

Memorization

Anti-Neuron Watermarking: Protecting Personal Data Against Unauthorized Neural Networks

2021-09-18 · Zihang Zou, Boqing Gong, Liqiang Wang

We study protecting a user's data (images in this work) against a learner's unauthorized use in training neural networks. It is especially challenging when the user's data is only a tiny percentage of the learner's compl…